Code Gen
Generate code, boilerplate, scaffolding
sql-optimization-patterns
by hwatkins
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
hypothesis-tracker
by biruk741
Manages debugging session state and tracks hypotheses. Prevents hypothesis cycles and maintains investigation history.
skill-creator
by zhuxining
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
conductor-dev
by imansmallapple
Professional project orchestration and workflow management. Initialize the Conductor directory to manage tracks, specifications, and implementation plans.
INVOGUE COLLAB HQ — Cowork Setup & Deployment Guide
by invogueai
Campaign budget tracked in real-time, warning at 80%, blocked at 100%
orizu-cli
by raveeshbhalla
Operate and troubleshoot the Orizu CLI for authentication and workspace operations. Use when Codex must run or explain orizu commands for login/logout/whoami, team and member management, project/app lifecycle, dataset upload/download/append/delete-rows (csv/json/jsonl), and task lifecycle (create/assign/status/export), including interactive selection fallbacks and non-interactive flag requirements.
using-superpowers
by Jackiexiao
（中文）Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
create-pr
by YPYT1
Streamlines pull request creation by handling the entire workflow: creating a new branch, committing changes, formatting modified files with Biome, and submitting the PR.
code-of-conduct-generator
by ehtbanton
Generate CODE_OF_CONDUCT.md files based on Contributor Covenant. Triggers on "create code of conduct", "generate code_of_conduct.md", "community guidelines", "contributor covenant".
bun
by zhongjis
Initializes projects, manages dependencies, runs scripts, executes tests, and bundles code using Bun. Use when working with package.json, installing packages, running dev servers, or building for production.
mocking-patterns
by karchtho
Jest mocking patterns, jest.fn(), jest.mock(), spies, module mocking, dependency injection, mock implementations. Activates when user mentions "mock", "jest.fn", "jest.mock", "spy", "stub", "fake", "dependency injection testing", or wants to isolate code for testing.
gen-log-kline
by samuerio
"Generate LOG K-line artifacts from symbol + trade time by auto-resolving trade metadata from local trade CSV files."
yt-outline
by naveedharri
Build detailed step-by-step YouTube video outlines with demo prep, screen-share sequences, and visual
portfolio-rebalance-tax-calc
by zen-tradings
Calculates the tax cost of rebalancing a portfolio and finds the most tax-efficient path from the current allocation to a target allocation. Use when the user asks about rebalancing, adjusting asset allocation, "how to rebalance without paying too much tax", "tax-efficient rebalancing", "change my allocation from X to Y", "reduce my stock exposure", "move money from stocks to bonds", or any question about changing portfolio weights while minimizing taxes. Also triggers when users mention being overweight or underweight in something, want to de-risk, or are considering a major portfolio restructuring. Covers multi-account rebalancing, tax-lot optimization, and phased transition plans.
chatnut
by runno-ai
Use when spawning agent teams that need shared discussion visibility beyond hub-and-spoke DMs
add-event-type
by slurpyb
Add a new event type to the frontend feed system with corresponding React component. Use when user mentions "new event", "add event type", "event block", "new block type", or wants to display new agent output types.
reprompter
by tutayworks
Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptverse", "run with quality", "smart run", "smart agents", "multi-agent marketing", "campaign swarm", "engineering swarm", "ops swarm", "research swarm", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptverse per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
charmkeeper-tests
by seb4stien
Use this skill when you need to write, update, migrate or fix unit tests.
csv-data-synthesizer
by ehtbanton
Generate realistic CSV data files with proper headers, data types, and configurable row counts for testing, demos, and development. Triggers on "create CSV data", "generate CSV file", "fake CSV for", "sample data CSV", "test data spreadsheet".
docs-writer
by idotta
Always use this skill when the task involves writing, reviewing, or editing files in the /docs directory or any .md files in the repository.
context7-skill-generator
by jovermier
Automatically generates skills from Context7 MCP documentation responses
agentmail
by albertpurnama
Give AI agents their own email inboxes using the AgentMail API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, handling attachments, organizing with labels, creating drafts for human approval, or setting up real-time notifications via webhooks/websockets. Supports multi-tenant isolation with pods.
update
by biruk741
Incrementally update AI documentation. Two modes — (1) add a new concept with the right doc types for each agent, (2) propagate a concept change across all existing AI docs. Use when you need to add, change, or remove a specific convention, rule, or pattern across your documentation. Triggers on "update docs", "change rule", "add convention", "propagate change", "update documentation".
agent-handoff
by gsailing19
Use when dispatching multiple agents, orchestrating agent pipelines, or coordinating parallel subagents where upstream output must survive context compression. Triggers for multi-agent workflows, parallel agent coordination, and text-intensive tasks (research, analysis, writing). Do NOT trigger for single-agent tasks, general AI agent discussions, or noun phrases where "agent" is not a dispatched tool (e.g. "travel agent", "browser user-agent", "real estate agent", "reinforcement learning agent").